end of 2 Working with data

sortolavi · sortolavi · commit 453e157cdcfa · 2026-02-01T14:37:30.000+02:00
diff --git a/Work/.vscode/settings.json b/Work/.vscode/settings.json
@@ -0,0 +1,5 @@
+{
+  "workbench.editor.autoLockGroups": {
+    "terminalEditor": false
+  }
+}
diff --git a/Work/Data/missing.csv b/Work/Data/missing.csv
@@ -0,0 +1,8 @@
+name,shares,price
+"AA",100,32.20
+"IBM",,91.10
+"CAT",150,83.44
+"MSFT",,51.23
+"GE",95,40.37
+"MSFT",50,65.10
+"IBM",100,70.44
diff --git a/Work/exercise.2.26.py b/Work/exercise.2.26.py
@@ -0,0 +1,31 @@
+import csv
+
+f = open('.\\Data\\dowstocks.csv')
+rows = csv.reader(f)
+headers = next(rows) # ['name', 'price', 'date', 'time', 'change', 'open', 'high', 'low', 'volume']
+# row = next(rows) # ['AA', '39.48', '6/11/2007', '9:36am', '-0.18', '39.67', '39.69', '39.45', '181800']
+
+types = [str, float, str, str, float, float, float, float, int]
+
+# record = { name: func(val) for name, func, val in zip(headers, types, row) }
+# print(record)
+# {'name': 'AA', 'price': 39.48, 'date': '6/11/2007', 'time': '9:36am', 'change': -0.18, 'open': 39.67, 'high': 39.69, 'low': 39.45, 'volume': 181800}
+
+records = [ { name: func(val) for name, func, val in zip(headers, types, row) } for row in rows]
+print(records[:3])
+# [{'name': 'IBM', 'price': 91.10, 'date': '5/13/2007', 'time': '4:20pm', 'change': 0.56, 'open': 90.54, 'high': 91.20, 'low': 90.50, 'volume': 183900}, {'name': 'CAT', 'price': 83.44, 'date': '9/23/2006', 'time': '1:30pm', 'change': -0.12, 'open': 83.56, 'high': 83.80, 'low': 83.40, 'volume': 121500}, {'name': 'MSFT', 'price': 51.23, 'date': '5/17/2007', 'time': '10:30am', 'change': 0.15, 'open': 51.08, 'high': 51.30, 'low': 51.00, 'volume': 195500}]
+
+
+for record in records[:3]:
+  for name, val in record.items():
+      if name == 'date':
+          record[name] = tuple(val.split('/'))
+
+    
+
+print(records[:3])
+
+
+
+
+
diff --git a/Work/exercise2.23.py b/Work/exercise2.23.py
@@ -0,0 +1,37 @@
+# extracting data from csv file
+'''
+name,date,time,shares,price
+"AA","6/11/2007","9:50am",100,32.20
+"IBM","5/13/2007","4:20pm",50,91.10
+"CAT","9/23/2006","1:30pm",150,83.44
+"MSFT","5/17/2007","10:30am",200,51.23
+"GE","2/1/2006","10:45am",95,40.37
+"MSFT","10/31/2006","12:05pm",50,65.10
+"IBM","7/9/2006","3:15pm",100,70.44
+'''
+import csv
+
+f = open('.\\Data\\portfoliodate.csv')
+rows = csv.reader(f)
+headers = next(rows)
+print(headers)
+# ['name', 'date', 'time', 'shares', 'price']
+
+selected_rows = ['name', 'shares', 'price']
+
+indices = [headers.index(colname) for colname in selected_rows]
+print(indices)
+# [0, 3, 4]
+
+# editor.inlineSuggest.enabled set it false, then again true 31.1.2026
+
+row = next(rows)
+# turn a row into a dictionary
+# zip(selected_rows, indices) -> ('name', 0), ('shares', 3), ('price', 4)
+record = { colname: row[index] for colname, index in zip(selected_rows, indices)}
+# {'name': 'AA', 'shares': '100', 'price': '32.20'}
+
+portfolio = [ { colname: row[index] for colname, index in zip(selected_rows, indices)} for row in rows]
+print(portfolio)
+
+# [{'name': 'IBM', 'shares': '50', 'price': '91.10'}, {'name': ... ]
diff --git a/Work/exercise2.24.py b/Work/exercise2.24.py
@@ -0,0 +1,27 @@
+import csv
+
+types = [str, int, float]
+
+f = open('.\\Data\\portfolio.csv')
+rows = csv.reader(f)
+headers = next(rows)
+row = next(rows)
+print(row)
+
+print(types[1](row[1])*types[2](row[2]))
+
+r = list(zip(types, row))
+# [(<class 'str'>, 'AA'), (<class 'int'>, '100'), (<class 'float'>, '32.20')]
+
+converted = [func(val) for func, val in zip(types, row)] # [str('AA'), int('100'), float('32.20')]
+print(converted,'\t' , converted[1] * converted[2])
+# ['AA', 100, 32.2]    3220.0000000000005
+
+
+# { name: func(val) for name, func, val in zip(headers, types, row) }
+
+print(list(zip(headers, types, row))) # [('name', <class 'str'>, 'AA'), ('shares', ... ]
+
+record = { name: func(val) for name, func, val in zip(headers, types, row) }
+print(record) # {'name': 'AA', 'shares': 100, 'price': 32.2}
+
diff --git a/Work/exercise2.5.py b/Work/exercise2.5.py
@@ -0,0 +1,54 @@
+
+from collections import Counter
+
+portfolio = [
+    ('GOOG', 100, 490.1),
+    ('IBM', 50, 91.1),
+    ('CAT', 150, 83.44),
+    ('IBM', 100, 45.23),
+    ('GOOG', 75, 572.45),
+    ('AA', 50, 23.15)
+]
+
+# combine the shares for each stock
+total_shares = Counter()
+for name, shares, price in portfolio:
+    total_shares[name] += shares
+
+print(total_shares)
+
+# map each stock to a list of (shares, price) tuples
+from collections import defaultdict
+
+holdings = defaultdict(list)
+for name, shares, price in portfolio:
+    holdings[name].append((shares, price))
+
+print(holdings)
+
+
+
+# https://www.geeksforgeeks.org/python/deque-in-python/
+# https://docs.python.org/3/library/collections.html#collections.deque
+from collections import deque
+
+filename = '.\\Data\\portfolio.csv'
+history = deque(maxlen=3)
+
+with open(filename) as f:
+    for line in f:
+        print(line, end='')  # show the line
+        history.append(line)
+
+print('Last 3 lines:')
+for line in history:
+    print(line, end='')
+
+pf = [{'name': 'AA', 'shares': '100', 'price': '32.20'}, {'name': 'IBM', 'shares': '50', 'price': '91.10'}, {'name': 'CAT', 'shares': '150', 'price': '83.44'}, {'name': 'MSFT', 'shares': '200', 'price': '51.23'}, {'name': 'GE', 'shares': '95', 'price': '40.37'}, {'name': 'MSFT', 'shares': '50', 'price': '65.10'}, {'name': 'IBM', 'shares': '100', 'price': '70.44'}]
+
+holdings = Counter()
+
+for stock in pf:
+    holdings[stock['name']] += int(stock['shares'])
+
+print(holdings)
diff --git a/Work/pcost.2.15.py b/Work/pcost.2.15.py
@@ -0,0 +1,37 @@
+# pcost.py
+#
+# Exercise 2.15
+#
+import csv
+
+def portfolio_cost(filename):
+    """Calculates the total cost of a stock portfolio from a CSV file with handling for missing files."""
+    value = 0.0
+    data_list = []
+
+    with open(filename, 'rt') as f:
+        rows = csv.reader(f)
+        headers = next(rows)   # take headers from first line
+
+        for linenum, line in enumerate(rows, start=2):
+            record = dict(zip(headers, line))
+            # print(record)
+            try:
+                num_shares = int(record['shares'])
+                price = float(record['price'])
+                value += num_shares * price
+                data_list.append(record)
+            except ValueError:
+                # print(f'Line {linenum}: Bad line: {line.strip()}')
+                print(f'Line {linenum}: Bad line: {line}')
+            
+    # return value
+    return data_list
+    
+      
+
+
+cost = portfolio_cost('.\\Data\\missing.csv')
+# print(f'Total cost of portfolio: ${cost}')
+print(cost)
+
diff --git a/Work/report.py b/Work/report.py
@@ -1,6 +1,6 @@
 # report.py
 #
-# Exercise 2.4
+# Exercise 2.4 - 2.12
 import csv
 from pprint import pprint
 
@@ -18,53 +18,89 @@ def read_prices(filename):
 
     return prices
 
-
 def read_portfolio(filename):
     """Reads a stock portfolio from a CSV file with handling for missing files."""
+    value = 0.0
     data_list = []
     
     try:
 
       with open(filename, 'rt') as f:
         rows = csv.reader(f)
         headers = next(rows) # skip the header line
-        for row in rows:
-            data_dict = {
-                'name': row[0],
-                'shares': int(row[1]),
-                'price': float(row[2])
-            }
-            data_list.append(data_dict)
-        return data_list
+
+        for rownum, row in enumerate(rows, start=2):
+            # data_dict = {
+            #     'name': row[0],
+            #     'shares': int(row[1]),
+            #     'price': float(row[2])
+            # }
+            record = dict(zip(headers, row))
+            try:
+                record['shares'] = int(record['shares'])
+                record['price'] = float(record['price'])
+                # value += num_shares * price
+                data_list.append(record)
+
+            except ValueError:
+                print(f'Line {rownum}: Bad line: {row}')
+            
+        return data_list, headers
       
     except FileNotFoundError:
       print(f'Error: The file {filename} was not found.')
       return None
 
+def make_report(portfolio, prices):
+    """Generates a report of the portfolio with current prices and gain/loss."""
+    report = []
+    for stock in portfolio:
+        name = stock['name']
+        shares = int(stock['shares'])
+        purchase_price = float(stock['price'])
+        current_price = prices.get(name, 0.0)
+        gain_loss = (current_price - purchase_price)
+        report.append((name, shares, current_price, gain_loss))
+    return report
+
+
 curr_prices = read_prices('.\\Data\\prices.csv')
-portfolio = read_portfolio('.\\Data\\portfolio.csv')
-# portfolio = read_portfolio('.\\Data\\missing.csv')
+portfolio = read_portfolio('.\\Data\\portfoliodate.csv')
+# print(portfolio[0])
+# print(portfolio[1])
+pf_data = portfolio[0]
+headers = portfolio[1]
+
+report = make_report(pf_data, curr_prices)
+
+for h in headers:
+    print('%10s' % h, end=' ')
+print()
+print(('-' * 10 + ' ') * len(headers))
 
-total_cost = 0.0
-total_gain_loss = 0.0
-curr_value = 0.0
+# for r in report:
+#     print('%10s %10d %10.2f %10.2f' % r)
 
-for s in portfolio: # loop through list of dictionaries
-    if s['name'] in curr_prices:
-       print(f"Updating {s['name']} price from {s['price']} to {curr_prices[s['name']]}")
-       s['current_price'] = curr_prices[s['name']]
-       s['gain_loss'] = (curr_prices[s['name']] - s['price']) * s['shares']
-       curr_value += curr_prices[s['name']] * s['shares']
-       
-       total_gain_loss += s['gain_loss']
-    total_cost += s['shares'] * s['price']
+# for name, shares, price, change in report:
+#     dollar_price = f'${price:0.2f}'
+#     print(f'{name:>10s} {shares:>10d} {dollar_price:>10s} {change:>10.2f}')
 
-pprint(portfolio)
+for row in pf_data:
+    # for i,j in row.items():
+    #     print(f'{j:>10s}', end=' ')
+    # print()
+    for i in list(row.values()):
+        print(f'{i:>10}', end=' ')
+    print()
 
-print(f'Total cost of portfolio: ${total_cost:0.2f} ${total_gain_loss:0.2f} gain/loss  Current value: ${curr_value:0.2f}\n')
 
-for s in portfolio:
-   print(f"{s['name']:6s}: {s['shares']:<6} shares at ${s['price']:0.2f}  Current price: ${s['current_price']:<6}  Gain/Loss: ${s['gain_loss']:0.2f}")
+
+    
+
+
+
+        
+
 
 
 

-Original file line number
+Diff line change
@@ @@ -0,0 +1,5 @@ @@
 +{
 +  "workbench.editor.autoLockGroups": {
 +    "terminalEditor": false
 +  }
 +}